Install¶
Pick the path for your machine. Builds aren't code-signed yet, so each OS will warn the first time — instructions for getting past the warning are inline.
macOS¶
Download Eternego.dmg. Open it, drag Eternego to Applications, then double-click Eternego from Applications.
The first launch shows: "Eternego.app cannot be opened because the developer cannot be verified." Right-click (or Control-click) the app, choose Open, then Open again in the dialog. macOS remembers the choice — subsequent launches are normal.
Windows¶
Download Eternego-setup.exe. Walk through the wizard (Next → Install → Finish). Eternego launches automatically and adds Start Menu and Desktop shortcuts.
The first dialog is "Windows protected your PC" (SmartScreen). Click More info, then Run anyway. SmartScreen remembers this app afterwards.
Linux (.AppImage)¶
Download Eternego-x86_64.AppImage, make it executable, run:
A single self-contained binary. No system Python needed.
Linux: unicode typing for screen control¶
If she uses screen control to type unicode (accented letters, em-dashes, emoji, anything outside US-ASCII), the kernel's uinput layer can't produce those characters directly — uinput is keycode-only and bound by the active keyboard layout. She routes through the system clipboard instead. Install the tool for your session type:
# Wayland (KDE, GNOME, sway, hyprland) — most modern Linux desktops
sudo pacman -S wl-clipboard # Arch / Manjaro
sudo apt install wl-clipboard # Debian / Ubuntu
sudo dnf install wl-clipboard # Fedora
# X11 — older desktops, or if XDG_SESSION_TYPE=x11
sudo pacman -S xclip
sudo apt install xclip
sudo dnf install xclip
Without one of these, ASCII typing still works (URLs, English text, code). Non-ASCII characters return a clear error pointing at the right package.
The Docker image ships with xclip pre-installed (the container runs an Xvfb desktop). If you're running native, install the package matching your session above.
Docker¶
The image ships with the persona's own desktop baked in (Xvfb + fluxbox + noVNC) — she can click, type, and install browsers herself when you ask. Peek at what she's doing at http://localhost:6080/vnc.html.
There's no prebuilt image to pull — you build it once from source (a few minutes), then it stays cached:
eterngit clone git.eternego.ai eternego-ai/eternego
cd eternego/installation/docker
docker compose up -d --build
Persona files live in ~/.eternego on the host — the same place the native install uses, so you can switch between Docker and native without losing data. Ollama running natively on the host is reached at host.docker.internal:11434 out of the box; edit docker-compose.yml inline for ports, GPU access, or a sibling Ollama container.
For the training-equipped image (~5.5 GB of CUDA wheels for LoRA fine-tuning), uncomment the INSTALL_TRAINING: "true" build arg in the compose file before up.
Background service (CLI, auto-start on boot)¶
The installers above launch when you open them. To register her as a system service so she keeps running across reboots:
# Linux (systemd) / macOS (launchd) — auto-installs Python via apt/dnf/pacman/brew. See "Local models" below for Ollama.
curl -fsSL https://git.eternego.ai/repos/eternego-ai/eternego/master/installation/install.sh | bash
# Windows (Scheduled Task) — auto-installs Python via winget
iwr -useb https://git.eternego.ai/repos/eternego-ai/eternego/master/installation/install.ps1 | iex
Both scripts accept --full (or -Full on Windows) to install training extras.
From source (contributors)¶
git clone [email protected]:eternego-ai/eternego.git
cd eternego
bash installation/install.sh # Linux/macOS
pwsh installation/install.ps1 # Windows
See CONTRIBUTING.md before sending a PR.
Local models (Ollama, optional)¶
Eternego works with cloud providers (Anthropic, OpenAI, xAI, Gemini, OpenRouter, Groq) out of the box — paste an API key when creating your persona. If you'd rather she run on local models — no API keys, no cloud calls — install Ollama separately:
# macOS
brew install ollama
# or download the installer from ollama.com/download
# Linux
curl -fsSL https://ollama.com/install.sh | sh
# Windows: download the installer from ollama.com/download
When you create a persona and select Local (Ollama) with a model name (e.g. qwen2.5:14b, llama3.1:8b, qwen2.5:32b), Eternego pulls it for you automatically. If Ollama isn't installed or running, you'll see a clear message pointing back here.
After install¶
Your browser opens to http://localhost:5000. If port 5000 is taken on your machine, the daemon picks the next free one and prints which it chose.
Continue to Your first persona →.